Inquiry about how to connect an existing, locally hosted Weaviate instance with pre-loaded embeddings as a knowledge base in the Agno framework without re-ingesting data

sham_sundar · July 4, 2025, 7:45pm

Hi,

For the agent’s knowledge, we need to use a locally hosted Weaviate vector database that already contains pre-generated embeddings.

We explored the knowledge base options you provided, but we couldn’t find a way to connect our existing Weaviate instance as a knowledge base without ingesting new data through your interface.

Since our Weaviate instance is already populated with data and embeddings, we want to connect to it as-is, without re-uploading or re-indexing anything.

Can you please guide us on how to achieve this?

Monali · July 7, 2025, 5:48am

Hey @sham_sundar, thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon.
If it’s urgent, please let us know. We appreciate your patience!

Latshawk · July 8, 2025, 11:46pm

Hi @Monali,

We are facing the same scenario, albiet a different vector database(milvus), but we would also like to know conceptually how to connect an existing vector database and want to use as-is.

WillemdeJongh1 · July 9, 2025, 8:49am

Hi @sham_sundar and @Latshawk

Thanks for raising your issues. We are planning on improving our Knowledge functionality and use cases like these are great.

If I understood your question correctly, you want to attach an existing Weaviate instance to an Agno KnowledgeBase.

Would you mind taking a look at this cookbook please. It shows how to connect a Weaviate DB to a KnowledgeBase. You won’t need to call the load() function if all of the documents you need are already embedded.
Please let me know if this satisfies your requirements and if not, what the issues are that you run into.

github.com/agno-agi/agno

cookbook/agent_concepts/knowledge/vector_dbs/weaviate_db/weaviate_db.py

main

"""
This example demonstrates using Weaviate as a vector database for semantic search.

Installation:
    pip install weaviate-client

You can use either Weaviate Cloud or a local instance.

Weaviate Cloud Setup:
1. Create account at https://console.weaviate.cloud/
2. Create a cluster and copy the "REST endpoint" and "Admin" API Key. Then set environment variables:
    export WCD_URL="your-cluster-url" 
    export WCD_API_KEY="your-api-key"

Local Development Setup:
1. Install Docker from https://docs.docker.com/get-docker/
2. Run Weaviate locally:
    docker run -d \
        -p 8080:8080 \
        -p 50051:50051 \

This file has been truncated. show original

Topic		Replies	Views
Weaviate Vector DB support General vectordb	4	32	April 8, 2025
WebsiteKnowledgeBase does not loading website content into DB General knowledge	1	31	February 19, 2025
Weaviate client connection closed after 1 query General knowledge	6	28	July 7, 2025
Managing Knowledge Entries in Vector DB (Add/Delete Files) - URGENT❗ General agent , knowledge	4	50	June 4, 2025
Migrate from CrewAI to Agno, how to reuse the embeddings from PGVector General vectordb , knowledge	2	44	May 5, 2025

Inquiry about how to connect an existing, locally hosted Weaviate instance with pre-loaded embeddings as a knowledge base in the Agno framework without re-ingesting data

Related topics